© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130154
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anth
    -0.27
     atoms
    -0.27
    åĨ¶
    -0.25
    åħ¬å®īå±Ģ
    -0.25
    atoms
    -0.25
    rollable
    -0.24
     Fold
    -0.24
     Rick
    -0.23
    transform
    -0.23
     dotyczÄħce
    -0.23
    POSITIVE LOGITS
    æĭ¾
    0.28
     pageCount
    0.26
    ä¼ij
    0.25
    legen
    0.24
    çļĦæĦŁåıĹ
    0.24
    KI
    0.24
    Ä±ÅŁÄ±
    0.24
    åį£
    0.24
    _TP
    0.23
     MessageBoxIcon
    0.23
    Activations Density 12.694%

    No Known Activations

    This feature has no known activations.